Notes for AFT Article

Cleaning

• Clean up tale names regex in atu
• Finish ATU sequences
• Clean up ID matches between atu and aft
• Reconcile use of older ATU ID by some aft texts

Exploratory analysis: What’s in the AFT corpus?

Tale Types

• By ATU Chapter/Division (n)
• Proportion of ATU represented by aft
• Find higher-order morphology in AFT. morphometric = set of motif groups that are combined in a tale type

By ATU Chapter

chapter	n_types	n_tales	tales_per
TALES OF MAGIC	240	607	2.529167
OTHER ANIMALS AND OBJECTS	50	104	2.080000
OTHER TALES OF THE SUPERNATURAL	36	72	2.000000
FORMULA TALES	53	93	1.754717
ANIMAL TALES	332	546	1.644578
RELIGIOUS TALES	543	782	1.440147
ANECDOTES AND JOKES	993	1218	1.226586

Content

Entities

• Find a well performing model for NER (cf. https://huggingface.co/flair/ner-english-ontonotes-fast, https://huggingface.co/stanfordnlp/stanza-en)
• Find a way to label the name of a main character (example Miller, prince, etc.) as more than simply a noun
• Pull out subject and predicate from sentence. Explore verbs related to subjects.

Common phrases using:

• TextRank
• collocation/word frequency

Topic modeling

• Define cleaning tasks and stop words to improve topic models performance; right now they are too close together, with a few main clusters of topics that are difficult to distinguish